A deep learning model for carotid plaques detection based on CTA images： a two stepwise early-stage clinical validation study
Bibliographic record
Abstract
Objective: To develop a deep learning (DL) model for carotid plaque detection based on CTA images and to evaluate the model’s precision and clinical application feasibility. Methods: We retrospectively collected data from patients with carotid atherosclerotic plaques who underwent continuous CTA examinations of the head and neck at a tertiary hospital from October 2020 to October 2022. The model combined ResUNet with the Pyramid Scene Parsing Network (PSPNet) to enhance plaque segmentation. Patient plaques were divided into training, validation, and testing sets in a ratio of 7:1.5:1.5. We analyzed recall (lesion-level sensitivity), sensitivity (patient-level), and precision to evaluate the model’s diagnostic performance for carotid plaques. The two stepwise early-stage clinical validation study (Comparison study and Model-human study) was used to simulate real clinical plaque diagnostic scenarios. Results: In total, 647 patients were included in the dataset, including 457 for training, 86 for validation, and 86 for testing. The DL model based on CTA images showed good precision in plaque diagnosis (validation set: precision=80.49%, sensitivity=90.70%, recall=84.62%; test set: precision=78.37%, sensitivity=91.86%, recall=84.58%). In addition, subgroup analysis of the plaque was carried out in the test set, and the precision of the model was evaluated based on plaque location (front, back, inside, and outside) and plaque morphology (smooth and non-smooth). The results showed that the recall of the plaque location was 83.72%, 76.32%, 89.25%, and 83.02%, respectively, and that for plaque morphology was 86.03% and 79.17%, respectively. The model had high accuracy in identifying plaques at different locations and with different morphologies. In the clinical application scenario analysis, the model’s diagnostic results for plaques were found to be higher than those of four out of six radiologists (p < 0.001). Furthermore, the use of this model was found to improve the recall rate of radiologists’ plaque diagnostic results. Additionally, the model’s diagnostic time for plaques (6s) was found to be significantly shorter than that of doctors (p < 0.001). Conclusion: Our research results indicate that the DL model for carotid plaque detection based on CTA images has high accuracy and clinical feasibility. The accuracy of plaque diagnosis is improved through model assisted diagnosis. Besides, the plaque detection time is significantly shortened, which has clinical value in reducing the workload of radiologists and improving the plaque detection rate.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.008 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".